Displaying 2 results from an estimated 2 matches for "sum_bb".
Did you mean:
sub_bw
2015 Jul 30
4
[LLVMdev] RFC: Callee speedup estimation in inline cost analysis
...of estimated speedup
(estimated reduction in dynamic instruction count to be precise) as
another factor that controls threshold. This would allow larger functions
whose inlining potentially reduces execution time to be inlined.
The dynamic instruction count of (an uninlined) function F is
DI(F) = Sum_BB(Freq(BB) * InstructionCount(BB))
* The above summation is over all basic blocks in F.
* Freq(BB) = BlockFrequency(BB)/BlockFrequency(Entry(F))
This dynamic instruction count measurement doesn't distinguish between a
single-cycle instruction and a long latency instruction. Instead of
using Ins...
2015 Jul 31
0
[LLVMdev] RFC: Callee speedup estimation in inline cost analysis
...timated reduction in dynamic instruction count to be precise) as
> another factor that controls threshold. This would allow larger functions
> whose inlining potentially reduces execution time to be inlined.
>
> The dynamic instruction count of (an uninlined) function F is
> DI(F) = Sum_BB(Freq(BB) * InstructionCount(BB))
>
> * The above summation is over all basic blocks in F.
> * Freq(BB) = BlockFrequency(BB)/BlockFrequency(Entry(F))
>
> This dynamic instruction count measurement doesn't distinguish between a
> single-cycle instruction and a long latency instr...